Commit Graph

10 Commits

Author SHA1 Message Date
6a446d9d73 convert pytorch's tensor in Python API (#1172)
* convert pytorch's tensor

* separate tests for convert pytorch tensor
2023-10-25 19:39:14 +01:00
eae94a451b PyO3: Add mkl support (#1159)
* Add `mkl` support

* Set `mkl` path on linux
2023-10-23 20:10:59 +01:00
cfb423ab76 PyO3: Add CI (#1135)
* Add PyO3 ci

* Update python.yml

* Format `bert.py`
2023-10-20 19:05:14 +01:00
6684b7127a PyO3: Add pytorch like .to() operator to candle.Tensor (#1100)
* add `.to()` operator

* Only allow each value to be provided once via `args` or `kwargs`
2023-10-19 21:46:21 +01:00
f9e93f5b69 Extend stub.py to accept external typehinting (#1102) 2023-10-17 11:07:26 +01:00
2c110ac7d9 Add the pooling operators to the pyo3 layer. (#1086) 2023-10-13 20:18:10 +01:00
75989fc3b7 Use an attention mask in the e5 padding case. (#1085) 2023-10-13 18:53:40 +01:00
904bbdae65 Make the Python Wrapper more Hackable and simplify Quantization (#1010)
* Some first `Module` implementations

* Add `state_dict` and `load_state_dict` functionality

* Move modules around and create `candle.nn.Linear`

* Add `nn.Embedding` and `nn.LayerNorm`

* Add BERT implementation

* Batch q-matmul

* Automatically dequantize `QTensors` if a `Tensor` is expected

* Add Module `.to()`, `.cuda()`, `cpu()` and `.type()` functionality

* Unittests for `Module`, `Tensor` and `candle.utils`

* Add `pytorch` like slicing to `Tensor`

* Cleanup and BERT fixes

* `black` formatting + unit-test for `nn.Linear`

* Refactor slicing implementation
2023-10-06 19:01:07 +01:00
03e194123d Add return types to *.pyi stubs (#880)
* Start generating return types

* Finish tensor type hinting

* Add `save_gguf` to `utils`

* Typehint `quant-llama.py`
2023-09-17 22:11:01 +01:00
8658df3485 Generate *.pyi stubs for PyO3 wrapper (#870)
* Begin to generate typehints.

* generate correct stubs

* Correctly include stubs

* Add comments and typhints to static functions

* ensure candle-pyo3 directory

* Make `llama.rope.freq_base` optional

* `fmt`
2023-09-16 17:23:38 +01:00